Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/73806
Title: Comparison of several forms of dimension reduction on quantitative morphological features for normal, abnormal and reactive lymphocyte differentiation
Author: Giménez Gredilla, Daniel
Tutor: Alférez, Santiago  
Others: Universitat Oberta de Catalunya
Abstract: Dimension reduction, or dimensionality reduction, is the process through which the number of variables observed in a study is reduced to a smaller number. The term Lymphoma defines a group of very common white blood cell cancers that affect both adult individuals and children. The correct diagnosis and treatment of lymphoma offers a significant survival rate. The Curse of Dimensionality is a common problem in which additional dimensions in data sets make information sparser. This can be managed by dimension reduction techniques. This study aims to compare the performance of PCA, ICA, Factor Analysis and LDA. LDA, PCA and Factor Analysis are shown to yield good results. A comparative table is given.
Keywords: lymphocytes
machine learning
factor analysis
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 2-Jan-2018
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
dgimenezgrTFM0118memoria.pdfMemoria del TFM1,8 MBAdobe PDFThumbnail
View/Open